Phage risk assessment for fermented dairy
A machine learning-based tool for fermented dairy manufacturing assesses and minimizes phage infection risks, enhancing production efficiency and quality by predicting and managing phage infections accurately.
Patent Information
- Application Number
- PCT/EP2025/059913
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-04-11
- Filing Date
- 2025-04-10
- Publication Date
- 2025-10-16
AI Technical Summary
Existing methods for assessing phage risk in fermented dairy product manufacturing are inadequate and lack precision, leading to inefficiencies in managing phage infections, which affect production times, yield, and product quality.
A dedicated tool and system using a mathematical model embedded in a user-friendly application to generate a risk score for different fermented dairy product manufacturing processes, incorporating machine learning models like trained neural networks to assess and minimize phage infection risks.
Provides an objective and standardized approach to predict and manage phage infections, reducing resource waste and improving production predictability by minimizing failures and maintaining product quality.
Smart Images

Figure EP2025059913_16102025_PF_FP_ABST
Abstract
Description
[0001] Phage risk assessment for fermented dairy
[0002] Technical Field
[0003] The present invention relates to the field of identifying an assessing the phage risks in dairies, to understand where phages can be a source of contamination in the process and to be able to manage it as best as possible. In particular, the present invention relates to a method and system for predicting the risk of phage contamination in a fermented dairy product manufacturing process using lactic acid bacteria.
[0004] Background
[0005] Phage-infections of dairy fermentations constitute a constant and commercially significant challenge for producers of fermented dairy (and non-dairy) products.
[0006] For manufacturing of fermented dairy products, it is desired to evaluate the risk of phage infection in dairy plants, to adjust the practice by e.g. cleaning cycles, strain rotations and / or product differentiation.
[0007] Patentee previously created a "Cleaning Tool" to guide e.g. cheesemakers to good manufacturing practice and thereby phage risk control. With 8 questions relating to cleaning, the dairy plant was assessed. With a limited number of questions it was very discriminative tool not optimal for problem solving, and it was not appropriate to all customers depending if they produced cheese of fresh dairy products.
[0008] Several approaches to improve the tool was attempted with limited success, why the inventors of present disclosure sought to solve the problem of proactive phage risk management in fermented dairy manufacturing.
[0009] Summary
[0010] As presented herein, a method and system for each segment of products was made by the inventors. More specifically, a dedicated tool was created for specific cheese segments as e.g. Continental cheese, Soft cheese, Cottage cheese, White Brine cheese, Pasta Filata, Cheddar. It is an object of the invention to provide a method and system for accurately and precisely assessing the manufacturing practice, estimating phage risk and thereby managing the risk of phage infections.
[0011] Brief Description of the Drawings
[0012] Fig. 1 is an example of the input conditions for a cottage cheese manufacturing process. The output risk score is shown as the total overall score in the bottom right cell of the table.
[0013] Fig. 2 is an example of the input conditions for a Pasta Filata cheese manufacturing process. The output risk score is shown as the total overall score in the bottom right cell of the table.
[0014] Fig. 3 is an example of the input conditions for a Pasta Filata cheese manufacturing process. The output risk score is shown as the total overall score in the bottom right cell of the table. The use of the risk score and how it translates to phage infection management is illustrated by the arrow and legend below the input table.
[0015] Detailed Description
[0016] Some of the embodiments contemplated herein may be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.
[0017] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where a step must necessarily follow or precede another step due to some dependency. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features, and advantages of the enclosed embodiments will be apparent from the following description.
[0018] As shown herein, a model, such as a mathematical model, is provided and embedded in a user-friendly application, such as a computer implemented system, so that a user, such as a cheese manufacturer or supervisor, is able to numerically generate a risk score for different fermented dairy product manufacturing process conditions.
[0019] The phage risk score may be an important parameter in production of fermented dairy products, and linked processes such as cleaning and selection of lactic acid bacteria.
[0020] By providing such a model as described herein, it is possible to assess the risk of phage infection before starting the manufacturing process e.g. by adding the lactic acid bacteria to the milk. This allows to minimize the risks of phage infections, and avoid extended production times, yield losses and inferior product quality.
[0021] Furthermore, an objective and standardized approach for assessing the risk of phage infections is provided which is independent from experts.
[0022] By applying the methods as disclosed herein, fermented dairy product can be manufactured with higher predictability and less resource waste since the risk of production failures due to phage infections are minimized.
[0023] It will be apparent to those skilled in the art that various modifications and variations can be made in the entities and methods of this invention as well as in the construction of this invention without departing from the scope or spirit of the invention.
[0024] The invention has been described in relation to particular embodiments and examples which are intended in all aspects to be illustrative rather than restrictive.
[0025] Those skilled in the art will appreciate that many different combinations of hardware, software and / or firmware will be suitable for practicing the present invention. Further, persons skilled in the art of manufacturing fermented dairy products will readily understand common terms, features, abbreviations, and process parameters related to manufacturing of fermented dairy products as disclosed herein.
[0026] As descriptive examples, the invention relates to the following embodiments: Embodiment 1: A computer implemented method for assessing the risk of phage infection in a fermented dairy product manufacturing process, said method comprising the steps of: receiving a plurality of fermented dairy product manufacturing process conditions; inputting the plurality of fermented dairy product manufacturing process conditions into a model to generate a risk score; and outputting the risk score generated by the model, the risk score predicting the phage infection risk in the fermented dairy product manufacturing process.
[0027] Embodiment 2: The computer implemented method according to embodiment 1, wherein the risk score is used to determine means to minimize the risk of phage infections.
[0028] Embodiment 3: The computer implemented method according to embodiment 1 or 2, wherein the plurality of fermented dairy manufacturing process conditions comprises a plurality of milk, bacterial culture and / or manufacturing parameters.
[0029] Embodiment 4: The computer implemented method according to any of embodiments 1 to 3, wherein the plurality of fermented dairy product manufacturing process conditions comprise at least conditions relating to Vat and Production Environment, Clean In Place (CIP) systems, Cleaning, Disinfection, Culture Dosage and Usage, Raw Materials.
[0030] Embodiment 5: The computer implemented method according to any of embodiments 2- 4, wherein the means to minimize the risk of phage infections comprise changing lactic acid bacterial cultures in intervals such as e.g. weekly, daily, twice daily or with every vat fill.
[0031] Embodiment 6: The computer implemented method according to any one of embodiments 1 to 5, wherein the model is differentiated between types of fermented dairy product types. Embodiment 7: The computer implemented method according to embodiment 6, wherein the fermented dairy product types comprise cheese types such as e.g. Continental cheese, Soft cheese, Cottage cheese, White Brine cheese, Pasta Filata and / or Cheddar.
[0032] Embodiment 8: The computer implemented method according to embodiment 6 or 7, wherein the fermented dairy product types comprise types such as e.g. Set yogurt, Stirred yogurt, Cream cheese and / or Faisselle.
[0033] Embodiment 9: The computer implemented method according to any one of embodiments 1 to 8, wherein the model is a trained machine learning model such as e.g. a trained neural network.
[0034] Embodiment 10: The computer implemented method according to any one of embodiments 1 to 9, wherein the trained machine learning model has been optimized on a training set comprising input-output pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score.
[0035] Embodiment 11: A method for assessing the risk of phage infection in a fermented dairy product manufacturing process, said method comprising the steps of: receiving a plurality of fermented dairy product manufacturing process conditions; inputting the plurality of fermented dairy product manufacturing process conditions into a model; and outputting the risk score generated by the model, the risk score predicting the phage infection risk in the fermented dairy product manufacturing process.
[0036] Embodiment 12: The method according to embodiment 11, wherein the phage infection risk score is used to determine means to minimize the risk of phage infections.
[0037] Embodiment 13: The method according to embodiment 12 wherein the means to minimize the risk of phage infections comprise changing lactic acid bacterial cultures in intervals such as e.g. weekly, daily, twice daily or with every vat fill.
[0038] Embodiment 14: A system for assessing the risk of phage infections in a fermented milk product process using a lactic acid bacterium, said system comprising: a processing unit configured to: receive a plurality of predetermined fermented dairy product manufacturing conditions; input the plurality of fermented dairy product manufacturing conditions into a model to generate a risk score; and output the risk score generated by the model, the risk score predicting the risk of phage infection in the fermented dairy product process, to optionally determine means to minimize the risk of phage infections.
[0039] Embodiment 15: The method according to embodiment 14, wherein the model is a trained machine learning model such as e.g. a trained neural network.
[0040] Embodiment 16: The system according to embodiment 15, wherein the plurality of fermented dairy product manufacturing process conditions comprise at least conditions relating to Vat and Production Environment, Clean In Place (CIP) systems, Cleaning, Disinfection, Culture Dosage and Usage, Raw Materials.
[0041] Embodiment 17: The system according to any of embodiments 14 to 16, wherein the model is differentiated between types of fermented dairy product types.
[0042] Embodiment 18: The system according to any one of embodiments 14 to 17, wherein the fermented dairy product types comprise types such as e.g. Continental cheese, Soft cheese, Cottage cheese, White Brine cheese, Pasta Filata and / or Cheddar.
[0043] Embodiment 19: The system according to any one of embodiments 14 to 18, wherein the fermented dairy product types comprise types such as e.g. Set yogurt, Stirred yogurt, Cream cheese and / or Faisselle.
[0044] Embodiment 20: The system according to embodiment any of embodiments 14 to 19, wherein the trained machine learning model has been optimized on a training set comprising input-output pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score.
[0045] Embodiment 21: The system according to any one of embodiments 14 to 20, wherein the trained machine learning model has been optimized on a training set comprising inputoutput pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score. Moreover, other implementations of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended that the specification and the examples be considered as exemplary only. To this end, it is to be understood that inventive aspects lie in less than all features of a single foregoing disclosed implementation or configuration. Thus, the true scope and spirit of the invention is indicated by the following claims.
Claims
Claims1. A computer implemented method for assessing the risk of phage infection in a fermented dairy product manufacturing process, said method comprising the steps of: receiving a plurality of fermented dairy product manufacturing process conditions; inputting the plurality of fermented dairy product manufacturing process conditions into a model to generate a risk score; and outputting the risk score generated by the model, the risk score predicting the phage infection risk in the fermented dairy product manufacturing process.
2. The computer implemented method according to claim 1, wherein the risk score is used to determine means to minimize the risk of phage infections.
3. The computer implemented method according to claim 1 or 2, wherein the plurality of fermented dairy manufacturing process conditions comprises a plurality of milk, bacterial culture and / or manufacturing parameters.
4. The computer implemented method according to any of claims 1 to 3, wherein the plurality of fermented dairy product manufacturing process conditions comprise at least conditions relating to Vat and Production Environment, Clean In Place (CIP) systems, Cleaning, Disinfection, Culture Dosage and Usage, Raw Materials.
5. The computer implemented method according to any of claims 2-4, wherein the means to minimize the risk of phage infections comprise changing lactic acid bacterial cultures in intervals such as e.g. weekly, daily, twice daily or with every vat fill.
6. The computer implemented method according to any one of claims 1 to 5, wherein the model is differentiated between types of fermented dairy product types.
7. The computer implemented method according to claim 6, wherein the fermented dairy product types comprise cheese types such as e.g. Continental cheese, Soft cheese, Cottage cheese, White Brine cheese, Pasta Filata and / or Cheddar.
8. The computer implemented method according to claim 6 or 7, wherein the fermented dairy product types comprise types such as e.g. Set yogurt, Stirred yogurt, Cream cheese and / or Faisselle.
9. The computer implemented method according to any one of claims 1 to 8, wherein the model is a trained machine learning model such as e.g. a trained neural network.
10. The computer implemented method according to any one of claims 1 to 9, wherein the trained machine learning model has been optimized on a training set comprising input-output pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score.
11. A method for assessing the risk of phage infection in a fermented dairy product manufacturing process, said method comprising the steps of: receiving a plurality of fermented dairy product manufacturing process conditions; inputting the plurality of fermented dairy product manufacturing process conditions into a model; and outputting the risk score generated by the model, the risk score predicting the phage infection risk in the fermented dairy product manufacturing process.
12. The method according to claim 11, wherein the phage infection risk score is used to determine means to minimize the risk of phage infections.
13. The method according to claim 12 wherein the means to minimize the risk of phage infections comprise changing lactic acid bacterial cultures in intervals such as e.g. weekly, daily, twice daily or with every vat fill.
14. A system for assessing the risk of phage infections in a fermented milk product process using a lactic acid bacterium, said system comprising: a processing unit configured to: receive a plurality of predetermined fermented dairy product manufacturing conditions; input the plurality of fermented dairy product manufacturing conditions into a model to generate a risk score; and output the risk score generated by the model,the risk score predicting the risk of phage infection in the fermented dairy product process, to optionally determine means to minimize the risk of phage infections.
15. The method according to claim 14, wherein the model is a trained machine learning model such as e.g. a trained neural network.
16. The system according to claim 15, wherein the plurality of fermented dairy product manufacturing process conditions comprise at least conditions relating to Vat and Production Environment, Clean In Place (CIP) systems, Cleaning, Disinfection, Culture Dosage and Usage, Raw Materials.
17. The system according to any of claims 14 to 16, wherein the model is differentiated between types of fermented dairy product types.
18. The system according to any one of claims 14 to 17, wherein the fermented dairy product types comprise types such as e.g. Continental cheese, Soft cheese, Cottage cheese, White Brine cheese, Pasta Filata and / or Cheddar.
19. The system according to any one of claims 14 to 18, wherein the fermented dairy product types comprise types such as e.g. Set yogurt, Stirred yogurt, Cream cheese and / or Faisselle.
20. The system according to claim any of claims 14 to 19, wherein the trained machine learning model has been optimized on a training set comprising input-output pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score.
21. The system according to any one of claims 14 to 20, wherein the trained machine learning model has been optimized on a training set comprising input-output pairs, wherein the input is the plurality of fermented dairy product manufacturing process conditions and the output is the risk score.
Citation Information
Patent Citations
Monitoring and controlling bacteriophage pressure
WO2022034171A1